Learning Damage Representations with Sequence-to-Sequence Models

Natural hazards have caused damages to structures and economic losses worldwide. Post-hazard responses require accurate and fast damage detection and assessment. In many studies, the development of data-driven damage detection within the research community of structural health monitoring has emerged due to the advances in deep learning models. Most data-driven models for damage detection focus on classifying different damage states and hence damage states cannot be effectively quantified. To address such a deficiency in data-driven damage detection, we propose a sequence-to-sequence (Seq2Seq) model to quantify a probability of damage. The model was trained to learn damage representations with only undamaged signals and then quantify the probability of damage by feeding damaged signals into models. We tested the validity of our proposed Seq2Seq model with a signal dataset which was collected from a two-story timber building subjected to shake table tests. Our results show that our Seq2Seq model has a strong capability of distinguishing damage representations and quantifying the probability of damage in terms of highlighting the regions of interest.

Shake Table Tests of a Novel Low-rise Bolt-Assembled Precast Concrete Sandwich Wall Panel Structure

A novel low-rise bolt - assembled precast concrete sandwich wall panel structure for rural residential houses was proposed, in which the connections between wall and wall, and wall and floor were connected by high strength bolts and steel plates. The bolt joints can be easily installed and disassembled. They are replaceable to make the precast structure demountable and reassembled. All the components are connected together by the novel bolted connectors. This paper presents the shake-table tests of a full-scale two-story bolt-assembled precast concrete sandwich wall building. The results indicated that the proposed structural system had good seismic performance and remained in the elastic stage with no damage after 9-degree rare earthquake excitation for the Model-1. The Model-2 exhibited excellent capacity and performed satisfactorily under the excitation up to 0.8 g. Cracks were observed at the wall openings and the base of walls and columns, which was similar to that of a cast-in-situ structure. The damage statuses were mainly light damage and moderate damage. The bolt connection joints were not anti-seismic weak places and had good seismic performance. Equivalent base shear method is suitable for estimating the seismic demand of the proposed precast concrete sandwich wall panel structure.